Machine learning-based prediction of friction torque and friction coefficient in statically loaded radial journal bearings


BAŞ H., KARABACAK Y. E.

TRIBOLOGY INTERNATIONAL, vol.186, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 186
  • Publication Date: 2023
  • Doi Number: 10.1016/j.triboint.2023.108592
  • Journal Name: TRIBOLOGY INTERNATIONAL
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Aerospace Database, Applied Science & Technology Source, Chimica, Communication Abstracts, Compendex, INSPEC, Metadex, Civil Engineering Abstracts
  • Keywords: Friction coefficient, Friction torque, Machine learning, Radial journal bearing, Tribological systems
  • Karadeniz Technical University Affiliated: Yes

Abstract

In this research, we utilized machine learning (ML) algorithms to predict the friction torque and friction coef-ficient in a statically loaded radial journal bearing. The study investigated the influence of temperature, bearing load, and rotational speed on the variation in friction torque and friction coefficient. Three different ML algo-rithms, namely, Artificial Neural Network (ANN), Support Vector Machine (SVM), and Regression Trees (RT), were applied to experimental tribological data. Performance assessment demonstrated that ML-based models can successfully predict the variation of friction torque and friction coefficient. Furthermore, we conducted a comparative analysis to evaluate the performance of ML-based models in relation to each other. The results of this study have useful implications for the design and optimization of statically loaded radial journal bearings.